AI Red Teamer/Penetration Tester

Mindgard
London
1 week ago
Applications closed

Related Jobs

View all jobs

AI Red Teamer/Penetration Tester

Information Security Engineer

AI - Internal Technical Security Consultant

Information Security Consultant - AI

Director of AI Cybersecurity Strategy (UK) (Hiring Immediately)

IT Manager

Mindgard is a London-based startup specializing in AI security. Our mission is to secure the future of AI Applications against cyber attacks. We've spun out from a leading UK university after a decade of R&D and are among the first few companies globally to offer solutions to this rapidly growing problem.

Mindgard's automated AI red teaming product helps security testers test for, identify, and remediate vulnerabilities in AI applications.

Mindgard probes AI applications and uses a set of techniques, including Predictive AI, LLMs, and other algorithms to identify security-relevant attributes within application responses.

We're seeking an experienced AI Red Teamer who will be responsible for uncovering security vulnerabilities within AI. You will identify vulnerabilities that our customers care about, demonstrate successful cyber attacks, and report your findings to internal and external stakeholders.

Roles & Responsibilities

In this role you will:

  1. Red team and penetration test AI models, systems, and applications.
  2. Work with customers, AI providers, and the open-source community to disclose new security issues and help secure their AI solutions.
  3. Collaborate with engineering and research to design, implement, and report attacks against AI models and applications.
  4. Generate company awareness via regular engagement with the security community through publishing articles, releasing publicly available tools, and presentations.
  5. Stay up to date on the latest AI security research, trends, and attack techniques.
  6. Contribute to the development of internal tools, our AI red teaming product, and open-source projects.


Skills & Experience

We are looking for:

  1. Strong experience in red teaming and penetration testing.
  2. Hands-on experience and understanding of attack techniques specific to AI applications (prompt injection, jailbreaking, model extraction, etc.).
  3. Familiarity with AI red teaming tools and LLM vulnerability scanners (PyRit, Garak, etc.), as well as established pentesting tools (Burp Suite, Nessus, etc.).
  4. Able to communicate with technical and non-technical stakeholders.
  5. Excellent problem-solving skills and creativity to find and anticipate potential attack vectors against AI applications.


Before you go, we want you to know!

Studies have shown that some groups of people are less likely to apply to a role unless they meet 100% of the job requirements. Whoever you are, if you don't meet all of the above criteria, but you think you'd be a great addition to Mindgard, we encourage you to apply as you might just be the candidate we hire. Our people are our strongest asset and the unique skills and perspectives people bring to the team are the driving force of our success. As an equal opportunity employer, we do not discriminate on the basis of any protected attribute. Our commitment is to provide equal opportunities, an inclusive work environment, and fairness for everyone.#J-18808-Ljbffr

Get the latest insights and jobs direct. Sign up for our newsletter.

By subscribing you agree to our privacy policy and terms of service.

Industry Insights

Discover insightful articles, industry insights, expert tips, and curated resources.

Quantum-Enhanced AI in Cyber Security: Guarding the Digital Frontier

The cyber security landscape has evolved dramatically over the past decade. Long gone are the days when businesses primarily worried about simplistic phishing or basic website defacements. Today’s threats include nation-state attacks, sophisticated ransomware, AI-generated phishing campaigns, and a wide array of stealthy intrusion methods. Organisations must defend vast digital ecosystems that include cloud infrastructure, IoT devices, and critical operational technology—any of which can become high-value targets for malicious actors. Amid these escalating challenges, a new technological wave is emerging: quantum computing. Although still in its infancy, quantum computing promises capabilities that could surpass even the most advanced classical supercomputers for specific tasks. Simultaneously, in the world of Artificial Intelligence (AI)—where data volumes and model complexity are exploding—quantum’s parallelism could significantly boost analysis, training, and decision-making. What unfolds when quantum computing and AI converge in the realm of cyber security? On one hand, quantum technologies could introduce stronger encryption and faster threat detection. On the other, adversaries armed with quantum power might break today’s cryptographic protocols or develop more potent attacks at unimaginable speeds. This article explores the phenomenon of quantum-enhanced AI for cyber security: the possibilities it unlocks, the challenges it poses, and the reasons it could reshape both defensive and offensive operations in the digital world.

Cyber Security Jobs at Newly Funded UK Start-ups: Q3 2025 Investment Tracker

Cyber security is no longer just a topic for tech-savvy professionals—it’s an essential pillar of every modern organisation. From protecting sensitive customer data to thwarting state-sponsored attacks, cyber security teams play a crucial role in safeguarding digital infrastructures across all sectors. In the UK, cyber security innovation is thriving, fuelled by a fertile mix of venture capital, government backing, and an ever-growing pool of talented specialists. Now, in the third quarter of 2025, we’ve seen a fresh influx of funding for cyber security start-ups that are poised to shape the industry’s future. This Q3 2025 Investment Tracker highlights newly funded UK-based cyber security start-ups, their core offerings, and—most importantly—the wide range of job opportunities they’re creating. Whether you’re a veteran security analyst, a pen tester, or a newcomer eager to explore the defensive side of tech, these start-ups are actively seeking professionals to help drive their next phase of growth. We’ll also guide you through the essential skills in demand, strategies to secure a role, and how to leverage CyberSecurityJobs.tech to fast-track your job search.

Portfolio Projects That Get You Hired for Cyber Security Jobs (With Real GitHub Examples)

With rising cyber threats and increasingly sophisticated attacks, cyber security has become a critical priority for organisations worldwide. From penetration testers (pentesters) and SOC analysts to cloud security engineers and threat intelligence specialists, the demand for skilled cyber security professionals continues to surge. But how do you stand out in a growing field? Alongside your CV, an impressive cyber security portfolio can be the distinguishing factor that convinces employers you’re the right fit. In this comprehensive guide, you’ll discover: Why a cyber security portfolio is essential for job seekers in this domain. How to align portfolio projects with different cyber security career paths. Real GitHub examples that demonstrate best practices in security-focused projects. Actionable project ideas you can start today, from penetration testing labs to blue-team detection pipelines. Best practices for organising your repos and presenting your work so hiring managers can instantly see your impact. When you’re ready to pursue your next opportunity, remember to upload your CV on CyberSecurityJobs.tech. Our specialised platform connects talented security professionals with employers who need your expertise—exactly what your portfolio will showcase.